Sync from GitHub repo

This Space is synced from the GitHub repo: https://github.com/SWivid/F5-TTS. Please submit contributions to the Space there

pyproject.toml

@@ -15,7 +15,7 @@ classifiers = [
 ]
 dependencies = [
     "accelerate>=0.33.0",
-    "bitsandbytes>0.37.0",
+    "bitsandbytes>0.37.0; platform_machine != 'arm64' and platform_system != 'Darwin'",
     "cached_path",
     "click",
     "datasets",

src/f5_tts/api.py

@@ -3,7 +3,6 @@ import sys
 from importlib.resources import files
 
 import soundfile as sf
-import torch
 import tqdm
 from cached_path import cached_path
 
@@ -43,9 +42,12 @@ class F5TTS:
         self.mel_spec_type = vocoder_name
 
         # Set device
-        self.device = device or (
-            "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
-        )
+        if device is not None:
+            self.device = device
+        else:
+            import torch
+
+            self.device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
 
         # Load models
         self.load_vocoder_model(vocoder_name, local_path=local_path, hf_cache_dir=hf_cache_dir)

src/f5_tts/infer/speech_edit.py

@@ -1,5 +1,7 @@
 import os
 
+os.environ["PYTOCH_ENABLE_MPS_FALLBACK"] = "1"  # for MPS device compatibility
+
 import torch
 import torch.nn.functional as F
 import torchaudio

src/f5_tts/infer/utils_infer.py

@@ -3,6 +3,7 @@
 import os
 import sys
 
+os.environ["PYTOCH_ENABLE_MPS_FALLBACK"] = "1"  # for MPS device compatibility
 sys.path.append(f"../../{os.path.dirname(os.path.abspath(__file__))}/third_party/BigVGAN/")
 
 import hashlib
@@ -33,8 +34,6 @@ from f5_tts.model.utils import (
 _ref_audio_cache = {}
 
 device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
-if device == "mps":
-    os.environ["PYTOCH_ENABLE_MPS_FALLBACK"] = "1"
 
 # -----------------------------------------